INDEX

Explanations

concepts related to privacy and truthfulness

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-0.81

er

-0.80

displayquote

-0.76

}),

-0.75

первых

-0.75

Figure

-0.73

sertation

-0.72

gios

-0.72

anyol

-0.71

 resourceCulture

-0.70

POSITIVE LOGITS

 Inſ

0.97

truth

0.96

Eſ

0.93

 Houſe

0.93

 Truth

0.92

 SEAT

0.91

 Diſ

0.91

 Anſ

0.90

 Jefus

0.89

 whoſe

0.88

Activations Density 0.076%

concepts related to privacy and truthfulness

No Comments

No Known Activations